Hybrid speech recognition

摘要

Described is a technology by which speech is locally and remotely recognized in a hybrid way. Speech is input and recognized locally, with remote recognition invoked if locally recognized speech data was not confidently recognized. The part of the speech that was not confidently recognized is sent to the remote recognizer, along with any confidently recognized text, which the remote recognizer may use as context data in interpreting the part of the speech data that was sent. Alternative text candidates may be sent instead of corresponding speech to the remote recognizer.

主权项

1. A method, comprising:
receiving handwriting input at a first device; executing, at the first device, handwriting recognition on the handwriting input to render a first recognition result comprising first text derived from the handwriting input; evaluating confidence in at least a portion of the first recognition result; in response to identification of a confidence evaluation for at least a portion of the first recognition result as being below a threshold level, sending data pertaining to at least a first portion of the handwriting input to a second device different from the first device and sending the first text to the second device, wherein the threshold level varies based on a speed of communication of the first device with the second device; and receiving from the second device a second recognition result comprising second text derived from the data.